Task 4 - Cleaning

library(tidyverse)
library(janitor)
library(here)
library(readxl)
library(lubridate)
library(stringr)

source("data_cleaning_scripts/bb_candy_clean_2015.R")

Warning: NAs introduced by coercion

dim(bb_candy_2015)

[1] 5630  124

pivot_2015_test <- bb_candy_2015 %>% 
  pivot_longer(cols = ("[Butterfinger]":"[York Peppermint Patties]"),
               names_to = "sweets",
               values_to = "enjoyment")

pivot_select_2015_test <- pivot_2015_test %>% 
  select(Timestamp, `How old are you?`, `Are you going actually going trick or treating yourself?`, sweets, enjoyment)
dim(pivot_2015_test)

[1] 523590     33

Clean up bb_candy_2015

Clean up bb_candy_2016

bb_candy_2016_string_to_lower <- bb_candy_2016_date %>% 
  mutate(country = str_to_lower(country))

bb_candy_2016_str_replace_test <- bb_candy_2016_string_to_lower %>% 
  mutate(country = str_replace_all(country, "us", "usa"),
         country = str_replace_all(country, "usaa", "usa"),
         country = str_replace_all(country, "united states of america", "usa"),
         country = str_replace_all(country, "merica", "usa"),
         country = str_replace_all(country, "usa!", "usa"),
         country = str_replace_all(country, "u.s.", "usa"),
         country = str_replace_all(country, "usa usa usa", "usa"),
         country = str_replace_all(country, "united sates", "usa"),
         country = str_replace_all(country, "units states", "usa"),
         country = str_replace_all(country, "usa usa", "usa"),
         country = str_replace_all(country, "the yoo ess of aaayyyyyy", "usa"),
         country = str_replace_all(country, "murica", "usa"),
         country = str_replace_all(country, "the best one - usa", "usa"),
         country = str_replace_all(country, "trumpistan", "usa"),
         country = str_replace_all(country, "units state", "usa"),
         country = str_replace_all(country, "united states", "usa"),
         country = str_replace_all(country, "united state", "usa"),
         country = str_replace_all(country, "united stetes", "usa"),
         country = str_replace_all(country, "usa!!!!!", "usa"),
         country = str_replace_all(country, "usaa.", "usa"),
         country = str_replace_all(country, "usasa", "usa"),
         country = str_replace_all(country, "usa \\((i think but it's an election year so who can really tell\\))", "usa"),
         country = str_replace_all(country, "cascadia", "usa"),
         country = str_replace_all(country, "NANA\\..+NA", "usa"),
         country = str_replace_all(country, "the republic of cascadia", "usa"),
         country = str_replace_all(country, "[0-9]", "NA"),
         country = str_replace_all(country, "united kingdom", "uk"),
         country = str_replace_all(country, "united kindon", "uk"),
         country = str_replace_all(country, "united kingdon", "uk"),
         country = str_replace_all(country, "united kindom", "uk"),
         country = str_replace_all(country, "england", "uk")
         )


bb_candy_2016_country_count_test <- bb_candy_2016_str_replace_test %>%
  distinct(country) %>% 
  summarise(n())
bb_candy_2016_country_count_test

distinct_country_remove <- bb_candy_2016_str_replace_test %>% 
  distinct(country)
view(distinct_country_remove)

Clean up bb_candy_2017

Clean countries test

bb_candy_2017_str_to_lower <- bb_candy_2017_select %>% 
  mutate(country = str_to_lower(country))

bb_candy_2017_str_replace_test7 <- bb_candy_2017_str_to_lower %>% 
  mutate(change_to_na = str_detect(country, "[0-9]"), .after = country) %>%  
  mutate(country = ifelse(change_to_na, NA, country))


bb_candy_2017_str_replace_test_usa <- bb_candy_2017_str_replace_test7 %>% 
  mutate(country = str_remove_all(country, "[:punct:]"),
         country = str_replace_all(country, ".*usa.*", "usa"),
         country = str_replace_all(country, "united s.*", "usa"),
         country = str_replace_all(country, "unites.*", "usa"),
         country = str_replace_all(country, "unied states", "usa"),
         country = str_replace_all(country, "unite states", "usa"),
         country = str_replace_all(country, ".merica", "usa"),
         country = str_replace_all(country, ".*usa", "usa"),
         country = str_replace_all(country, "u s.*", "usa"),
         country = str_replace_all(country, "^us$", "usa"),
  

         country = str_replace_all(country, "unhinged states", "usa"),
         country = str_replace_all(country, "ahemamerca", "usa"),
         country = str_replace_all(country, "u s a", "usa"),
         country = str_replace_all(country, ".usa", "usa"),
         country = str_replace_all(country, "murica", "usa"),
         
         country = str_replace_all(country, "new york", "usa"),
         country = str_replace_all(country, "new jersey", "usa"),
         country = str_replace_all(country, "california", "usa"),
         country = str_replace_all(country, "north carolina", "usa"),
         country = str_replace_all(country, "pittsburgh", "usa"),
         country = str_replace_all(country, "murrika", "usa"),
         country = str_replace_all(country, "murica", "usa"),
         country = str_replace_all(country, "nusa", "usa"),
         country = str_replace_all(country, "alaska", "usa"),
         country = str_replace_all(country, "trumpistan", "usa"),
         country = str_replace_all(country, "merica", "usa")
  )


bb_candy_2017_str_replace_test_canada2 <- bb_candy_2017_str_replace_test_usa %>% 
    mutate(country = str_replace_all(country, "canada`", "canada"),
           country = str_replace_all(country, "can.*", "canada"),
           country = str_replace_all(country, "soviet canuckistan", "canada"),
           country = str_replace_all(country, "soviet canada", "canada"))

bb_candy_2017_str_replace_uk <- bb_candy_2017_str_replace_test_canada2 %>%
    mutate(country = str_replace_all(country, "united kingdom", "uk"),
           country = str_replace_all(country, "scotland", "uk"),
           country = str_replace_all(country, "england", "uk")
           )

bb_candy_2017_str_to_lower_new <- bb_candy_2017_str_replace_uk %>% 
  group_by(country) %>% 
  distinct() %>% 
  summarise(n())


bb_candy_2017_str_to_lower_og1 <- bb_candy_2017_str_to_lower %>% 
  group_by(country) %>% 
  distinct() %>% 
  summarise(n())

view(bb_candy_2017_str_to_lower_new)
view(bb_candy_2017_str_to_lower_og1)

  
view(bb_candy_2017_distinct_country)
view(bb_candy_2017_str_to_lower_og)